Samoth

@carlitacrypto_ Trop cool bravo!

Petite annonce qui me tient à cœur 🤍 Ça fait 4 ans que je crée du contenu sur la crypto. Et depuis un moment, l'IA a pris une vraie place dans mon quotidien : dans mes process, dans les projets sur lesquels je bosse, dans les conversations que j'ai avec mes potes le soir. Ces deux sujets sont devenus mes deux obsessions, et j'ai envie de leur donner plus de place. Donc voilà, je lance officiellement carlitacrypto.com 🎉 Vous allez y trouver tout ce que je fais au même endroit, mes nouveaux contenus, et surtout une newsletter mensuelle où je vous partagerai ce qui m'aura marquée dans la crypto et l'IA. Genre les trucs que je dirais à mes potes en soirée, mais en version organisée. 👉 carlitacrypto.com Merci d'être là depuis le début, vraiment 🥹

@AlexanderKaln1 Just tried it and it worked perfectly an dI even won the round hehe

What happens when you turn trading into a fantasy draft game? 👾 You draft assets instead of players. Pick direction (long/short) and leverage for each one. Once everyone’s locked in, you choose a captain → 2x leverage on that pick. Then it’s live. 3 minutes. Real markets. Your P&L decides the winner. No charts. No overthinking. Just picks → execution → outcome. Built this in ~1 day using @Mithril_money (~$20 in compute). You just need to add your @pacifica_fi api credentials, and start playing: meme-fantasy-draft.mithril.money Feels like we’ll see a lot more of this: perp DEX = liquidity + execution game = interface Would you play this? @AnthoLGSB @danieldelophem @Jordanwithluv @_guynemer @givenoxbt

🚨 Alpha Friday - Time Change 🚨 youtube.com/live/ADBguqF8T… We’re going live tomorrow at 12:00 UTC (usually 13:00 - 1 hour earlier) Agenda: • Community updates • Publish for yourself • Preview: “Publish for users” (shareable apps) • UX improvements (streamlined keys + login) • Live build → publish demo This one’s a big step forward. See you there 👇

@stevibe This is awesome will try asap

I built a macOS app for benchmarking local LLMs. 6 test suites. Multiple providers. One workspace. Open source. There are hundreds of local models now. New ones every week. How do you actually pick one? Leaderboards test for general ability. But if you're building an agent that chains tool calls, or a pipeline that extracts structured data, or a code assistant that needs to debug Rust, you need to know if the model handles that specific thing. Not in theory. On your hardware. With your prompts. The benchmarks that exist are either locked behind papers, too abstract to map to real failures, or impossible to extend. You can't add your own test cases. You can't test what matters to your use case. That's what BenchLocal is for. It's a benchmark platform where every test is practical, deterministic, and built around real-world tasks. And you can build your own tests. It ships with 6 Bench Packs TODAY: → ToolCall-15 — tool-use accuracy → BugFind-15 — debugging capabilities → DataExtract-15 — structured data extraction → InstructFollow-15 — constraint-heavy instruction following → ReasonMath-15 — practical reasoning and math → StructOutput-15 — validator-backed structured output Every pack has 15 fixed scenarios. Every score is deterministic and verifiable. Some of you saw ToolCall-15 and BugFind-15 — the individual test packs I open-sourced over the past few weeks. People ran them, filed issues, sent PRs. But managing separate repos, separate scripts, separate results doesn't scale. BenchLocal puts everything in one place. What the app does: > Workspace with tabs — run BugFind-15 in one tab, ToolCall-15 in another. > Any provider — Ollama, llama.cpp, OpenRouter, any OpenAI-compatible endpoint. Local and cloud, same interface. > Run modes — serial, batch per model, batch per test case, or fully parallel. > Test histories — every run saved. Compare any previous session. But the part I'm most excited about isn't the app. It's the ecosystem. BenchLocal is a platform. Each Bench Pack is a plugin. I'm shipping an SDK so anyone can build their own — test what matters to you, package it, share it. Install and uninstall packs right inside the app, same way you'd manage extensions in VS Code. The registry is GitHub-based, fully public. I built 6 packs. I want the community to build the next 60. Theme system built in too — because if I'm staring at benchmark results for hours, it should at least look good. v0.1.0 is macOS only. Windows and Linux are coming. MIT licensed. Everything — the app, the bench packs, the SDK — is open. PRs welcome. Bench Packs even more welcome.

Alpha Friday is back tomorrow (17th of April) at 12:00 UTC ⚒️ youtube.com/watch?v=iAALkz… We’re building live: “My Bank” app → Dashboard → Savings goals → Delta-neutral yield → Multiple accounts → Growth projections Also covering: → Community stats (bots, volume, growth) → Template giveaway 🎁 From idea → working financial app Live. No edits. What should we build next? 👀 Drop it below 👇

@jonrhythmic @mithril_money Hey, sorry for the issue, it's a known bug we're working on, you can go to api.mithril.money and disconnect then reconnect on build.mithril.money and it should work

@mithril_money Testing your beta, but I get this errormessage: [Error: Session expired. Use the 'Reset auth' button above the chat input to fix it.] Where is the Reset auth button?

Mithril App Builder is live in BETA ⚒️ No waitlist. No setup. No friction. You describe what you want in plain English: → “Build me a trading bot” 📊 → “Create a delta-neutral strategy with execution” ⚖️ → “Show a live portfolio dashboard with PnL + analytics” 📈 And it ships a working app. Not a demo. Not a mockup. A real React application with: live market data ⚡ execution wired in 🔌 a usable dashboard 📊 Already happening: • 898+ trading bots created 🤖 • $380M+ non-custodial volume shipped 💰 Under the hood: • One unified API → 7+ perp DEXs + prediction markets 🔗 • Non-custodial execution layer running 24/7 ⏱️ • AI Builder that turns ideas into working systems 🧠 What builders are shipping right now: • Prediction market systems & prediction tools 📊 • Automated trading bots & arbitrage scanners 🤖 • Delta-neutral + spread strategies ⚖️ • Real-time portfolio dashboards & analytics 📈 • Signal-based execution pipelines ⚡ This is the shift: From → “I have an idea” 💡 To → “I have a working app” ⚒️ In minutes. No more wiring APIs. ❌ No more managing infra. ❌ No more rebuilding dashboards from scratch. ❌ 👉 build.mithril.money What’s the first thing you’re building? Kalshi edge? Delta-neutral stack? A dashboard that actually prints? 💰 Drop your idea below 👇 We’re reading every single one. Let’s ship real edges ⚒️

Build any web3 app in minutes with Mihtril

The demo video was narrated by my own cloned voice, recorded in French, generated in English by the skill itself.

Stack: • Claude Code skill (one SKILL.md file) • ElevenLabs Python SDK • Your API key • That's it No server, no daemon, no build step. GitHub: github.com/thomasblc/elev…

I built a Claude Code skill for @ElevenLabs Text to speech, voice cloning, batch audio from markdown, sound effects — all from the terminal. One SKILL.md file. Open source.

@mal_shaik i feel like 1/10th of my prompts is exactly being pissed at claude for pushing on vercel every 2 min

claude code core

@melvynx Minimax quite decent tbh

Search the Opus 4.6 replacement for my OpenClaw: day 1 I tried Kimi 2.5 today. It's not good. It has issues with tool calls. It outputs Chinese characters. It's bad... really bad. What's next?

Am I the only one that is getting crazy usage on @claudeai suddenly? Always was able to avoir usage session limit and now just got hit after 1hr in the session

@Alexintosh That’s so cool, was always so frustrated that we dont have the mirror iphone in ue

Specchio🪞 The EU friendly iPhone Mirroring app. worked on: ᐧ stable connection ᐧ revised ux ᐧ continuity between usb / wifi basically ready for early testers

The perp wars are raging above… …but deep in the Mithril mines, something actually useful is coming online. We just scanned CT again. Builders are still screaming: → 14-hour Polymarket bot installs full of malware and dep hell → AI agents that look fire in demo then crash in prod → Full-stack web3 breakage (wagmi + viem + indexing = months of pain) → Perp traders glued 12+ hrs/day watching funding bleed them dry Enough. Pre-flight check… ✅ Execution layer live ✅ Unified API across 7+ perp DEXs + prediction markets ✅ Builder → Beta Opens Soon +898 trading bots already created +$370M in real trading volume (non-custodial, real money) Now it’s your turn to stop the infra tax. Mithril Builder nukes the exact pains we keep seeing: • Trading bots & Polymarket bots (no more malware repos or 14-hour terminal nightmares) • Delta-neutral strategies & hedge fund-style setups • Arbitrage scanners & signal-based execution • Market-making, grid, momentum scalping, copy-trading • Yield optimizers & USDC vaults • Portfolio dashboards & automated TA • Strategy testing tools & market data dashboards • Treasury management & structured strategies • Full agentic systems (no babysitting brittle agents) Describe your edge in plain English → AI spits out a working React bot + real-time dashboard. One API. 98% uptime. Built-in monitoring, dynamic spreads, stop-loss, arbitrage finder. Build whatever you want. No custody. No trading advice. Just pure execution infra. Comment “BUILD” for early access Who’s tired of the 14-hour setup tax? Drop your worst bot story below 👇